TransformersChartsAndPlotsAnalysis

Charts and plots analysis task

Subclass of Task.

Module: implementation.tasks

Default predictor

This task uses TransformersGenerativeModel by default with this configuration:

model = Pix2StructForConditionalGeneration.from_pretrained(
    "google/deplot"
)
predictor=TransformersGenerativeModel(
    TransformersModelConfig(
        model=model,
        kwargs={
            "max_new_tokens": 512
        }
    ),
    input_class=TransformersChartsAndPlotsModelInput,
    output_class=TransformersBasicOutput
)

See:

• TransformersGenerativeModel

• TransformersModelConfig

• TransformersChartsAndPlotsModelInput

• TransformersBasicOutput

Methods and properties

Main methods and properties

---

__init__

Arguments:

• predictor (Predictor[Any, Any], optional): Predictor that will be used in task. If equals to None, default predictor will be used. Defaults to None.

• preprocess (Optional[Component], optional): Component executed before predictor. If equals to None, default component will be used. Defaults to None. Default component: ChartsAndPlotsAnalysisPreprocessor If default chain is used, ChartsAndPlotsAnalysisPreprocessor will use Pix2StructProcessor from model used in predictor.

• postprocess (Optional[Component], optional): Component executed after predictor. If equals to None, default component will be used. Defaults to None. Default component: ChartsAndPlotsAnalysisPostprocessor If default chain is used, ChartsAndPlotsAnalysisPostprocessor will use Pix2StructProcessor from model used in predictor.

• input_class (Type[Input], optional): Class for input validation. Defaults to ChartsAndPlotsAnalysisInput.

• output_class (Type[Output], optional): Class for output validation. Defaults to TransformersBasicOutput.

• name (Optional[str], optional): Name for identification. If equals to None, class name will be used. Defaults to None.

---

---

---

ChartsAndPlotsAnalysisInput

Subclass of IOModel.

---

__init__

Arguments:

• image (Image.Image): Image to analyze.

• text (str): Text prompt.

---

---

---

ChartsAndPlotsAnalysisPreprocessor

Prepare model input. Subclass of Action. Type of Action[Dict[str, Any], Dict[str, Any]].

---

__init__

Arguments:

• processor (Processor): Feature extractor.

---

execute

Arguments:

• input_data (Dict[str, Any]): Expected keys:

  • "text" (str): Text prompt;

  • "image" (Image.Image): Image to analyze;

Returns:

• Dict[str, Any]: Expected keys:

  • "flattened_patches" (Any);

  • "attention_mask" (Any);

---

---

---

ChartsAndPlotsAnalysisPostprocessor

Process model output. Subclass of Action. Type of Action[Dict[str, Any], Dict[str, Any]].

---

__init__

Arguments:

• processor (Processor): Feature extractor.

• name (Optional[str], optional): Name for identification. If equals to None, class name will be used. Defaults to None.

---

execute

Arguments:

• input_data (Dict[str, Any]): Expected keys:

  • "output" (Any): Model output;

Returns:

• Dict[str, Any]: Expected keys:

  • "output" (str): Text representation of chart or plot;

---

---